python - scikit 分类器的准确率非常低(朴素贝叶斯、DecisionTreeClassifier)

Question

我正在使用这个数据集Weath Based on age并且文档指出准确度应在 84% 左右。不幸的是，我的程序的准确率是 25%

为了处理数据，我执行了以下操作:

1. Loaded the .txt data file and converted it to a .csv
2. Removed data with missing values
3. Extracted the class values: <=50K >50 and convert it to 0 and 1 respectively
4. For each attribute and for each string value of that attribute I 
   mapped it to an integer value. Example att1{'cs':0, 'cs2':1},
   att2{'usa':0, 'greece':1} ... and so on
5. Called naive bayes on the new integer data set

Python 代码:

import load_csv as load #my functions to do [1..5] of the list
import numpy as np

my_data = np.genfromtxt('out.csv', dtype = dt, delimiter = ',', skip_header = 1)

data = np.array(load.remove_missing_values(my_data))                     #this funcion removes the missing data
features_train = np.array(load.remove_field_num(data, len(data[0]) - 1)) #this function extracts the data, e.g removes the class in the end of the data

label_train = np.array(load.create_labels(data))
features_train = np.array(load.convert_to_int(features_train))


my_data = np.genfromtxt('test.csv', dtype = dt, delimiter = ',', skip_header = 1)

data = np.array(load.remove_missing_values(my_data))
features_test = np.array(load.remove_field_num(data, len(data[0]) - 1))

label_test = np.array(load.create_labels(data))                          #extracts the labels from the .csv data file
features_test = np.array(load.convert_to_int(features_test))             #converts the strings to ints(each unique string of an attribute is assigned a unique integer value

from sklearn import tree
from sklearn.naive_bayes import GaussianNB
from sklearn import tree
from sklearn.metrics import accuracy_score

clf = tree.DecisionTreeClassifier()
clf.fit(features_train, label_train)
predict = clf.predict(features_test)

score = accuracy_score(predict, label_test) #Low accuracy score

load_csv模块:

import numpy as np

attributes = {  'Private':0, 'Self-emp-not-inc':1, 'Self-emp-inc':2, 'Federal-gov':3, 'Local-gov':4, 'State-gov':5, 'Without-pay':6, 'Never-worked':7,
            'Bachelors':0, 'Some-college':1, '11th':2, 'HS-grad':3, 'Prof-school':4, 'Assoc-acdm':5, 'Assoc-voc':6, '9th':7, '7th-8th':8, '12th':9, 'Masters':10, '1st-4th':11, '10th':12,                  'Doctorate':13, '5th-6th':14, 'Preschool':15,
            'Married-civ-spouse':0, 'Divorced':1, 'Never-married':2, 'Separated':3, 'Widowed':4, 'Married-spouse-absent':5, 'Married-AF-spouse':6,
            'Tech-support':0, 'Craft-repair':1, 'Other-service':2, 'Sales':3, 'Exec-managerial':4, 'Prof-specialty':5, 'Handlers-cleaners':6, 'Machine-op-inspct':7, 'Adm-clerical':8, 
            'Farming-fishing':9, 'Transport-moving':10, 'Priv-house-serv':11, 'Protective-serv':12, 'Armed-Forces':13,
            'Wife':0, 'Own-child':1, 'Husband':2, 'Not-in-family':4, 'Other-relative':5, 'Unmarried':5,
            'White':0, 'Asian-Pac-Islander':1, 'Amer-Indian-Eskimo':2, 'Other':3, 'Black':4,
            'Female':0, 'Male':1,
            'United-States':0, 'Cambodia':1, 'England':2, 'Puerto-Rico':3, 'Canada':4, 'Germany':5, 'Outlying-US(Guam-USVI-etc)':6, 'India':7, 'Japan':8, 'Greece':9, 'South':10, 'China':11,                   'Cuba':12, 'Iran':13, 'Honduras':14, 'Philippines':15, 'Italy':16, 'Poland':17, 'Jamaica':18, 'Vietnam':19, 'Mexico':20, 'Portugal':21, 'Ireland':22, 'France':23,                  'Dominican-Republic':24, 'Laos':25, 'Ecuador':26, 'Taiwan':27, 'Haiti':28, 'Columbia':29, 'Hungary':30, 'Guatemala':31, 'Nicaragua':32, 'Scotland':33, 'Thailand':34, 'Yugoslavia':35,                  'El-Salvador':36, 'Trinadad&Tobago':37, 'Peru':38, 'Hong':39, 'Holand-Netherlands':40
      }



def remove_field_num(a, i):                                                                      #function to strip values
   names = list(a.dtype.names)  
   new_names = names[:i] + names[i + 1:]
   b = a[new_names]
   return b

def remove_missing_values(data):
    temp = []
    for i in range(len(data)):
        for j in range(len(data[i])):
            if data[i][j] == '?':                                                                 #If a missing value '?' is encountered do not append the line to temp
                break;
            if j == (len(data[i]) - 1) and len(data[i]) == 15:
                temp.append(data[i])                                                              #Append the lines that do not contain '?'
    return temp

def create_labels(data):
    temp = [] 
    for i in range(len(data)):                                                                    #Iterate through the data
        j = len(data[i]) - 1                                                                      #Extract the labels
        if data[i][j] == '<=50K':
            temp.append(0)
        else:
            temp.append(1)
    return temp

def convert_to_int(data):

    my_lst = []
    for i in range(len(data)):
        lst = []
        for j in range(len(data[i])):
            key = data[i][j]
            if j in (1, 3, 5, 6, 7, 8, 9, 13, 14):
                lst.append(int(attributes[key]))
            else:
                lst.append(int(key))    
        my_lst.append(lst)

    temp = np.array(my_lst)
    return temp

我尝试过使用tree和NaiveBayes，但准确率很低。对我缺少什么有什么建议吗？

Answer 1

我猜问题出在预处理中。最好将分类变量编码为 one_hot 向量(只有 0 或 1 的向量，其中 1 对应于该类的所需值)而不是原始数字。 sklearn DictVectorizer可以在这方面帮助你。您可以使用 pandas 库更有效地进行分类。

下面展示了在 pandas 库的帮助下如何轻松实现这一目标。它与 scikit-learn 一起工作得很好。在占整个数据 20% 的测试集上，准确率达到 81.6。

from __future__ import division

from sklearn.cross_validation import train_test_split
from sklearn.feature_extraction.dict_vectorizer import DictVectorizer
from sklearn.linear_model.logistic import LogisticRegression
from sklearn.metrics.classification import classification_report, accuracy_score
from sklearn.naive_bayes import GaussianNB
from sklearn.tree.tree import DecisionTreeClassifier

import numpy as np
import pandas as pd


# Read the data into a pandas dataframe
df = pd.read_csv('adult.data.csv')

# Columns names
cols = np.array(['age', 'workclass', 'fnlwgt', 'education', 'education-num',
                 'marital-status', 'occupation', 'relationship', 'race', 'sex',
                 'capital-gain', 'capital-loss', 'hours-per-week', 'native-country',
                 'target'])

# numeric columns
numeric_cols = ['age', 'fnlwgt', 'education-num',
                'capital-gain', 'capital-loss', 'hours-per-week']

# assign names to the columns in the dataframe
df.columns = cols

# replace the target variable to 0 and 1 for <50K and >50k
df1 = df.copy()
df1.loc[df1['target'] == ' <=50K', 'target'] = 0
df1.loc[df1['target'] == ' >50K', 'target'] = 1

# split the data into train and test
X_train, X_test, y_train, y_test = train_test_split(
    df1.drop('target', axis=1), df1['target'], test_size=0.2)


# numeric attributes

x_num_train = X_train[numeric_cols].as_matrix()
x_num_test = X_test[numeric_cols].as_matrix()

# scale to <0,1>

max_train = np.amax(x_num_train, 0)
max_test = np.amax(x_num_test, 0)        # not really needed

x_num_train = x_num_train / max_train
x_num_test = x_num_test / max_train        # scale test by max_train

# labels or target attribute

y_train = y_train.astype(int)
y_test = y_test.astype(int)

# categorical attributes

cat_train = X_train.drop(numeric_cols, axis=1)
cat_test = X_test.drop(numeric_cols, axis=1)

cat_train.fillna('NA', inplace=True)
cat_test.fillna('NA', inplace=True)

x_cat_train = cat_train.T.to_dict().values()
x_cat_test = cat_test.T.to_dict().values()

# vectorize (encode as one hot)

vectorizer = DictVectorizer(sparse=False)
vec_x_cat_train = vectorizer.fit_transform(x_cat_train)
vec_x_cat_test = vectorizer.transform(x_cat_test)

# build the feature vector

x_train = np.hstack((x_num_train, vec_x_cat_train))
x_test = np.hstack((x_num_test, vec_x_cat_test))


clf = LogisticRegression().fit(x_train, y_train.values)
pred = clf.predict(x_test)
print classification_report(y_test.values, pred, digits=4)
print accuracy_score(y_test.values, pred)

clf = DecisionTreeClassifier().fit(x_train, y_train)
predict = clf.predict(x_test)
print classification_report(y_test.values, pred, digits=4)
print accuracy_score(y_test.values, pred)

clf = GaussianNB().fit(x_train, y_train)
predict = clf.predict(x_test)
print classification_report(y_test.values, pred, digits=4)
print accuracy_score(y_test.values, pred)